Papers › What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks

What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks

27 Jun 2024arXiv:2406.18854archive 2025-07-28

Yilun Zheng, Sitao Luan, Lihui Chen

Graph homophily refers to the phenomenon that connected nodes tend to share similar characteristics. Understanding this concept and its related metrics is crucial for designing effective Graph Neural Networks (GNNs). The most widely used homophily metrics, such as edge or node homophily, quantify such "similarity" as label consistency across the graph topology. These metrics are believed to be able to reflect the performance of GNNs, especially on node-level tasks. However, many recent studies have empirically demonstrated that the performance of GNNs does not always align with homophily metrics, and how homophily influences GNNs still remains unclear and controversial. Then, a crucial question arises: What is missing in our current understanding of homophily? To figure out the missing part, in this paper, we disentangle the graph homophily into 3 aspects: label, structural, and feature homophily, providing a more comprehensive understanding of GNN performance. To investigate their synergy, we propose a Contextual Stochastic Block Model with 3 types of Homophily (CSBM-3H), where the topology and feature generation are controlled by the 3 metrics. Based on the theoretical analysis of CSBM-3H, we derive a new composite metric, named Tri-Hom, that considers all 3 aspects and overcomes the limitations of conventional homophily metrics. The theoretical conclusions and the effectiveness of Tri-Hom have been verified through synthetic experiments on CSBM-3H. In addition, we conduct experiments on 31 real-world benchmark datasets and calculate the correlations between homophily metrics and model performance. Tri-Hom has significantly higher correlation values than 17 existing metrics that only focus on a single homophily aspect, demonstrating its superiority and the importance of homophily synergy. Our code is available at https://github.com/zylMozart/Disentangle_GraphHom.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

zylmozart/disentangle_graphhom officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (5 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
4ran
1unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zylmozart/disentangle_graphhom. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

zylmozart/disentangle_graphhom official repository 11 samples, 10 ran (5 instrument-failed) · 1 unverified
cross_class_neighbor_similarity utils/homophily_metrics.py ran MIT (permissive) · 6c070d8d3769da17 · report fixture: signature A:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-24
edge_homophily in 6 papers homophily.py ran MIT (permissive) · 95ad75b3e583df53 · report fixture: signature edge_index:Tensor/2/int, labels:Tensor/1/int, ignore_negative:bool/0/bool · returned Tensor · level recorded 2026-09-24
neighborhood_homophily utils/homophily_metrics.py ran · our draft was wrong MIT (permissive) · bf40f9371cf13ba1 · report fixture: signature A:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-24
node_homophily in 6 papers homophily.py ran · our draft was wrong MIT (permissive) · aaa80033faca2aeb · report fixture: signature A:Tensor/2/float, labels:list/1/int · returned Tensor · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
utils/util_funcs.py ran · our draft was wrong MIT (permissive) · 7864a49a3e2da4fd · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-24
normalize_tensor in 47 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
utils/train_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 6784eb2b1dbf4455 · report fixture: signature mx:Tensor/2/float, symmetric:int/0/int · returned Tensor · level recorded 2026-09-24
remove_self_loops in 8 papers homophily.py ran · honoured contract fingerprinted MIT (permissive) · ef90ba6dacfae5eb · report fixture: signature edge_index:Tensor/2/int, edge_attr:Tensor/2/float · returned tuple · level recorded, date not recorded
spectral_radius_sp_matrix utils/train_utils.py ran MIT (permissive) · 6f63e8ed588c5c47 · report fixture: signature edge_index:ndarray/2/int, values:ndarray/1/float, num_nodes:int/0/int · returned float64 · level recorded 2026-09-24
spectral_radius_sp_matrix utils/util_funcs.py ran MIT (permissive) · ad582bcf67eada8c · report fixture: signature edge_index:ndarray/2/int, values:ndarray/1/float, num_nodes:int/0/int · returned float64 · level recorded 2026-09-24
sym_matrix utils/train_utils.py ran · our draft was wrong MIT (permissive) · d8014340a3d1f330 · report fixture: signature A:Tensor/2/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_pyg_dataset preprocess_dataset.py unverified MIT (permissive) · 0b2b4a99abaf17f1 · report

Tasks

Stochastic Block Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections